{"id":"https://openalex.org/W2140899792","doi":"https://doi.org/10.1109/chinasip.2013.6625311","title":"Structured mean field method for single-microphone speech separation with factorial Hidden Markov Model","display_name":"Structured mean field method for single-microphone speech separation with factorial Hidden Markov Model","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2140899792","doi":"https://doi.org/10.1109/chinasip.2013.6625311","mag":"2140899792"},"language":"en","primary_location":{"id":"doi:10.1109/chinasip.2013.6625311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17626003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"122","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216225266456604},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7014219164848328},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6631970405578613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6317436099052429},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5513630509376526},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.47273245453834534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40494146943092346},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.36344853043556213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34526675939559937},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07614782452583313}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216225266456604},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7014219164848328},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6631970405578613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6317436099052429},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5513630509376526},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.47273245453834534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40494146943092346},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.36344853043556213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34526675939559937},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07614782452583313},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/chinasip.2013.6625311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1528056001","https://openalex.org/W1560512119","https://openalex.org/W2015143272","https://openalex.org/W2059833849","https://openalex.org/W2079362249","https://openalex.org/W2098678088","https://openalex.org/W2103135337","https://openalex.org/W2106309817","https://openalex.org/W2109886546","https://openalex.org/W2120340025","https://openalex.org/W2130322773","https://openalex.org/W2144404214","https://openalex.org/W2152057158","https://openalex.org/W2168793898","https://openalex.org/W2169415915","https://openalex.org/W4293052541","https://openalex.org/W4297792526","https://openalex.org/W6633434192","https://openalex.org/W6684458083"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"A":[0],"variational":[1],"statistical":[2],"inference":[3,48,86,96],"method":[4,10,87],"referred":[5],"as":[6,93],"structured":[7],"mean":[8],"field":[9],"is":[11,53],"studied":[12,84],"for":[13],"factorial":[14],"Hidden":[15],"Markov":[16,28],"Model":[17],"(HMM)":[18],"formulation":[19],"of":[20,30,40,46,49,60,63,100,103],"single-microphone":[21],"speech":[22,33,42,51,70],"separation":[23,67,91],"problem.":[24],"By":[25],"decoupling":[26],"the":[27,31,37,41,44,50,58,64,76,83,89,94],"chains":[29],"individual":[32],"sources":[34,52],"coupled":[35],"during":[36],"mixing":[38],"process":[39],"mixture,":[43],"complexity":[45],"temporal":[47],"reduced":[54],"to":[55],"quadratic":[56],"with":[57],"number":[59],"acoustic":[61],"states":[62],"sources.":[65],"Speech":[66,104],"and":[68,107],"automatic":[69],"recognition":[71],"experiments":[72],"are":[73],"performed":[74],"on":[75],"reconstructed":[77],"speech.":[78],"Experimental":[79],"results":[80,92],"show":[81],"that":[82],"approximating":[85],"achieves":[88],"similar":[90],"exact":[95],"algorithm":[97],"in":[98],"terms":[99],"Perceptual":[101],"Evaluation":[102],"Quality":[105],"(PESQ)":[106],"word":[108],"error":[109],"rate":[110],"(WER).":[111]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}